Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction [PDF]
Computer Vision and Pattern Recognition, 2021 Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement in the coded aperture snapshot spectral imaging (CASSI) system.
Yuanhao Cai +7 more
semanticscholar +1 more source
RealFusion 360° Reconstruction of Any Object from a Single Image [PDF]
Computer Vision and Pattern Recognition, 2023 We consider the problem of reconstructing a full 360° photographic model of an object from a single image of it. We do so by fitting a neural radiance field to the image, but find this problem to be severely ill-posed.
Luke Melas-Kyriazi +3 more
semanticscholar +1 more source
NeRP: Implicit Neural Representation Learning With Prior Embedding for Sparsely Sampled Image Reconstruction [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2021 Image reconstruction is an inverse problem that solves for a computational image based on sampled sensor measurement. Sparsely sampled image reconstruction poses additional challenges due to limited measurements. In this work, we propose a methodology of
Liyue Shen, J. Pauly, Lei Xing
semanticscholar +1 more source
Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction [PDF]
International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022 We propose a novel and unified method, measurement-conditioned denoising diffusion probabilistic model (MC-DDPM), for under-sampled medical image reconstruction based on DDPM.
Yutong Xie, Quanzheng Li
semanticscholar +1 more source
Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning [PDF]
Computer Vision and Pattern Recognition, 2021 Fast and accurate reconstruction of magnetic resonance (MR) images from under-sampled data is important in many clinical applications. In recent years, deep learning-based methods have been shown to produce superior performance on MR image reconstruction.
Pengfei Guo +4 more
semanticscholar +1 more source
Deep Learning Image Reconstruction for CT: Technical Principles and Clinical Prospects.
Radiology, 2023 Filtered back projection (FBP) has been the standard CT image reconstruction method for 4 decades. A simple, fast, and reliable technique, FBP has delivered high-quality images in several clinical applications.
Lennart R. Koetzier +8 more
semanticscholar +1 more source
Specificity-Preserving Federated Learning for MR Image Reconstruction [PDF]
IEEE Transactions on Medical Imaging, 2021 Federated learning (FL) can be used to improve data privacy and efficiency in magnetic resonance (MR) image reconstruction by enabling multiple institutions to collaborate without needing to aggregate local data.
Chun-Mei Feng +4 more
semanticscholar +1 more source
Energy-efficient high-fidelity image reconstruction with memristor arrays for medical diagnosis
Nature Communications, 2023 Image reconstruction algorithms raise critical challenges in massive data processing for medical diagnosis. Here, the authors propose a solution to significantly accelerate medical image reconstruction on memristor arrays, showing 79× faster speed and ...
Han Zhao +11 more
semanticscholar +1 more source
Splatter Image: Ultra-Fast Single-View 3D Reconstruction [PDF]
Computer Vision and Pattern Recognition, 2023 We introduce the Splatter Image, an ultra-efficient approach for monocular 3D object reconstruction. Splatter Image is based on Gaussian Splatting, which allows fast and high-quality reconstruction of 3D scenes from multiple images.
Stanislaw Szymanowicz +2 more
semanticscholar +1 more source
Focal Frequency Loss for Image Reconstruction and Synthesis [PDF]
IEEE International Conference on Computer Vision, 2020 Image reconstruction and synthesis have witnessed remarkable progress thanks to the development of generative models. Nonetheless, gaps could still exist between the real and generated images, especially in the frequency domain.
Liming Jiang +3 more
semanticscholar +1 more source